mookiexl

I'm having the same issue. It happens with every custom checkpoint, and it started happening after the commit 52520c6 ("Merge branch 'universal_embeddings'", 2024-04-16) It seems like it's trying to pull...

Ok, so apparently it happens only when training a LoRA, finetune works. Clean install from scratch, clean VENV, changed preset to "SD 1.5 LoRA", everything else left at default. -Using...

Just noticed that @supermachine77 seems to be doing finetuning, based on "training_method": "FINE_TUNE", so there could also be another separate problem that also leads to the same "ValueError: Calling CLIPTokenizer.from_pretrained()...

Yes, it seems to work for me now. Thanks.

> I spent some hours debugging and had to change the line 265 in "/toolkit/prompt_utils.py" to make it to work : > > ` text_embeds = embed_list` by ` text_embeds...

You can make it use a local copy by giving it an absolute path to your local snapshot by giving it something along the lines of D:\models\stable_diffusion\mycheckpoint instead of huggingface...